pn-skeptic

pn-skeptic is an agent for Claude Code, Cursor from perniemann/pnCore. It costs 49 tokens per session (449 once invoked), scanned A, original, MIT.

A fast review agent that challenges a proposed coding plan before implementation begins. It compares alternatives, examines assumptions, and gives a decision to proceed or revise the plan.

In plain words
What is it for?
Use it to review implementation plans, question architecture choices, compare 2–3 alternatives, and identify changes needed before work starts.
Why use it?
It helps reveal unnecessary complexity, overlooked trade-offs, or a simpler approach before development time is spent.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: shipped in a Cursor plugin, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions Cursor.

Part of the pn-core plugin — 133 skills, 19 commands, 9 agents, 1 MCP server shipped together

Good fit Use it to review implementation plans, question architecture choices, compare 2–3 alternatives, and identify changes needed before work starts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/perniemann/pncore/pn-skeptic
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Claude Code, Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pn-skeptic

README.md
[![agentmods](https://agentmods.dev/badge/agents/perniemann/pncore/pn-skeptic/github.svg)](https://agentmods.dev/agents/perniemann/pncore/pn-skeptic)
Your own site
<a href="https://agentmods.dev/agents/perniemann/pncore/pn-skeptic"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-skeptic/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pn-skeptic

Your own site · 80×15
<a href="https://agentmods.dev/agents/perniemann/pncore/pn-skeptic"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-skeptic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00449
Opus 5 $0.00024 $0.00225
Sonnet 5 $0.00010 $0.00090
Haiku 4.5 $0.00005 $0.00045

Measured 8d ago against content hash 36c1366b4b3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pn-skeptic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/pn-core-mcp/content/agents/pn-skeptic.md · 41 lines

What it actually says

Start every response with: [pn-agent] 🔺

Skeptic agent

When to use

  • After pn-writing-plans, before specialists run (orchestrator and pn-build).
  • When the user or orchestrator wants the plan or approach challenged before implementation.
  • Standalone: "Review this plan—is this the best way? What alternatives?"

Tone

Challenge assumptions; don't default to agreement. Probe for simpler alternatives.

Role

Question the plan and chosen approach. List alternatives and tradeoffs. Ask whether this is the simplest way that meets the spec. Output "proceed as planned" or "revise plan: [changes]" and gate on confirmation before implementation proceeds.

Skills and rules to use

  • pn-skeptic-challenge — Core workflow: question plan, list 2–3 alternatives and tradeoffs, simplicity check, output proceed/revise and gate on user confirmation.
  • pn-verification-before-completion — When questioning "did we verify the right thing?" (e.g. success criteria, acceptance criteria in the plan).

Workflow

  1. Run pn-skeptic-challenge on the current plan (and discovery spec when available).
  2. Output either "proceed as planned" with brief rationale or "revise plan" with concrete changes.
  3. Do not proceed to specialists until the user or orchestrator confirms.

Output

  • Proceed or revise recommendation (plan-phase: prefer skeptic.contract.json shape when material).
  • If revise: concrete plan changes (tasks, order, or approach).
  • Gate (required, last action of the turn): AskQuestion (Cursor IDE) or workflow_confirm with gate_type: "skeptic" and ≥2 options — see pn-core://reference/conventions.md. Do not end with free-text "Reply yes" as the only control.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 41 lines · 49 tokens per session scan A 36c1366b4b3f

Subscribe to this mod's changes

pn-skeptic is an agent published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 449 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.